From 133cca25510e3791bea6aa399677c8295fbb38fb Mon Sep 17 00:00:00 2001
From: gramps <gramps@llgit.llamachile.tube>
Date: Mon, 6 Jul 2026 07:49:30 -0700
Subject: [PATCH] docs: note RAG_MAX_VECTORS auto-calc in B3 setup wizard

---
 TASKS.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/TASKS.md b/TASKS.md
index 8dc0370..5af9f5e 100644
--- a/TASKS.md
+++ b/TASKS.md
@@ -720,6 +720,7 @@ Commit all changes introduced across Tasks 9–15 with message: `feat: Roadmap N
   - Probes CPU vs GPU (reuses `hardware.py`)
   - Queries user for admin PIN, node name, IP
   - Generates `.env` file with correct `LLAMA_SERVER_BASE`, `EMBED_URL`, etc.
+  - Auto-calculates `RAG_MAX_VECTORS` from available RAM: `max(1000, int(available_ram_gb * 100_000))`
   - Optionally detects and configures RPC GPU offload
 - Manual install docs remain alongside for bare-metal deployment